kegg-database

Pass

Audited by Gen Agent Trust Hub on Apr 6, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill implements a straightforward wrapper for the KEGG REST API. Analysis of the scripts and instructions confirms that all network activity is limited to the official https://rest.kegg.jp domain.
  • [EXTERNAL_DOWNLOADS]: Fetches biological pathway and genomic data from the Kyoto Encyclopedia of Genes and Genomes (KEGG) REST API. This is a well-known and trusted service in the bioinformatics community.
  • [COMMAND_EXECUTION]: No shell commands or subprocess calls are present. The script exclusively uses the Python standard library's urllib module for web requests.
  • [DATA_EXFILTRATION]: No sensitive local data (such as credentials, SSH keys, or environment variables) is accessed or transmitted. The functions are designed to retrieve scientific data based on user queries.
  • [PROMPT_INJECTION]: The instructions in SKILL.md are descriptive and focus on guiding the agent to use the provided API helpers correctly. There are no attempts to override safety filters or hijack agent behavior.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 6, 2026, 11:30 PM
Security Audit — agent-trust-hub — kegg-database